diff --git a/doc/source/tutorials/04-comparing.ipynb b/doc/source/tutorials/04-comparing.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..ec747bcd855fbce6cb7ad012a5d2b677085d838a
--- /dev/null
+++ b/doc/source/tutorials/04-comparing.ipynb
@@ -0,0 +1,174 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Comparing scenes\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/bolirev/.virtualenvs/toolbox-navigation/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88\n",
+      "  return f(*args, **kwds)\n",
+      "/home/bolirev/.virtualenvs/toolbox-navigation/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility. Expected 96, got 88\n",
+      "  return f(*args, **kwds)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load the necessary modules\n",
+    "from navipy.database import DataBase\n",
+    "from matplotlib.image import imsave\n",
+    "import numpy as np\n",
+    "import os\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Load the database, and specify the\n",
+    "# the output directory to save the list\n",
+    "# of images\n",
+    "import pkg_resources\n",
+    "# Use the trafile from the resources\n",
+    "# You can adapt this code, by changing trajfile \n",
+    "# with your own trajectory file\n",
+    "database = pkg_resources.resource_filename(\n",
+    "    'navipy',\n",
+    "    'resources/database.db')\n",
+    "database_dir, _ = os.path.splitext(database)\n",
+    "if not os.path.exists(database_dir):\n",
+    "    os.makedirs(database_dir)\n",
+    "database_template = os.path.join(database_dir, 'frame_{}.png')\n",
+    "# Load two scene, currrent and memory\n",
+    "mydb = DataBase(database)\n",
+    "my_scene_current = mydb.scene(posorient=mydb.posorients.iloc[0])\n",
+    "my_scene_memory = mydb.scene(posorient=mydb.posorients.iloc[5])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Image differences\n",
+    "\n",
+    "Within a certain range of a goal location, the difference between memorized and currently experienced views can provide instructions on how to move towards the goal.\n",
+    "\n",
+    "The strong colour contrast of terrestrial objects against the sky may be of particular importance to localization and the demonstration that in outdoor scenes, panoramic image differences develop smoothly with distance from a reference location (translational Image Difference Functions, IDFs) and in addition, provide robust visual compass information (rotational IDFs) [Zeil 2012, Visual homing: an insect perspective].\n",
+    "\n",
+    "### Translational"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[1.09429471e-03],\n",
+       "       [1.22631411e-03],\n",
+       "       [5.04916451e-04],\n",
+       "       [2.91033150e+00]])"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from navipy.comparing import imagediff\n",
+    "tidf = imagediff(my_scene_current, my_scene_memory)\n",
+    "tidf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Rotational\n",
+    "\n",
+    "Rotational IDFs is done as follow: The current view is rotated by $\\alpha$ and compared pixelwise to the memorised image:\n",
+    "$$RIDF(\\alpha) = \\sum_i\\sum_j \\|rot(C(i,j),\\alpha) - M(i,j)\\| $$"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0,0.5,'IDF')"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from navipy.comparing import rot_imagediff\n",
+    "view_dir = mydb.viewing_directions\n",
+    "azimuth = view_dir[...,1]\n",
+    "# Calculate image diff\n",
+    "rotdf = rot_imagediff(my_scene_current, my_scene_memory)\n",
+    "# Place it in a dataframe with \n",
+    "# here index is alpha, the rotation\n",
+    "# of the current image\n",
+    "alpha = -np.linspace(0,np.max(azimuth)-np.min(azimuth),rotdf.shape[0])\n",
+    "alpha = np.deg2rad(alpha)\n",
+    "alpha = np.arctan2(np.sin(alpha),np.cos(alpha))\n",
+    "alpha = np.rad2deg(alpha)\n",
+    "rotdf = pd.DataFrame(index=alpha,columns = ['R','G','B','D'],data=rotdf)\n",
+    "# \n",
+    "rotdf.drop('D',axis=1).plot(style='.')\n",
+    "plt.xlabel('Rotated index')\n",
+    "plt.ylabel('IDF')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}